检索结果-内蒙古大学图书馆

International Conference on Information and Automation (ICIA)

作者： Dihong Gong Kai Zhu Zhifeng Li Yu Qiao Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9781479913329

Video-based face recognition has attracted a great deal of attention in recent years due to its wide applications. The challenge of video-based face recognition comes from several aspects. First, video data involves many frames, which increases data size and processing complexity. Second, key frames extracted from videos are usually of high intra-personal discrepancy due to variations in expressions, poses, and illuminations. In order to address these problems, we propose a novel semantic based subspace model to improve the performance of video based face recognition. The basic idea is to construct an appropriate low-dimensional subspace for each person, upon which a semantic model is built to classify the key frames of the person into specific class. After the semantic classification, the key frames belonging to the same classes, i.e. the same semantics, are used to train the linear classifiers for recognition. Extensive experiments on a large face video database (XM2VTS) clearly show that our approach obtains a significant performance improvement over the traditional approaches.

关键词： Face Training Face recognition Semantics Video sequences Principal component analysis Probes

来源：评论

学校读者我要写书评

暂无评论

ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression Framework

arXiv

引用

arXiv 2022年

作者： Mo, Ningkai Gan, Wanshui Yokoya, Naoto Chen, Shifeng ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China The University of Tokyo Japan RIKEN Japan

In this paper, a computation efficient regression framework is presented for estimating the 6D pose of rigid objects from a single RGB-D image, which is applicable to handling symmetric objects. This framework is designed in a simple architecture that efficiently extracts point-wise features from RGB-D data using a fully convolutional network, called XYZNet, and directly regresses the 6D pose without any post refinement. In the case of symmetric object, one object has multiple ground-truth poses, and this one-to-many relationship may lead to estimation ambiguity. In order to solve this ambiguity problem, we design a symmetry-invariant pose distance metric, called average (maximum) grouped primitives distance or A(M)GPD. The proposed A(M)GPD loss can make the regression network converge to the correct state, i.e., all minima in the A(M)GPD loss surface are mapped to the correct poses. Extensive experiments on YCB-Video and TLESS datasets demonstrate the proposed framework's substantially superior performance in top accuracy and low computational cost. The relevant code is available in https://***/GANWANSHUI/***. Copyright © 2022, The Authors. All rights reserved.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Spatio-temporal Network with Self-attention for Multi-station Passenger Flow Prediction

A Dynamic Spatio-temporal Network with Self-attention for Mu...

引用

International Conference on Awareness Science and Technology (iCAST)

作者： Fengzhi Wang Qinzhi Lv Lijuan Liu College of Computer and Information Engineering Xiamen University of Technology Xiamen China Fujian Key Laboratory of Pattern Recognition and Image Understanding

Passenger flow prediction is vitally significant for intelligent transportation systems (ITS). Most of the studies typically focus on the passenger flow prediction for an individual station, and only capture the temporal features without considering any spatial features. Constructing a passenger flow prediction model for multiple stations, or even a whole network, is more valuable for practical applications. Therefore, we develop a dynamic spatio-temporal network (DSTNet) with a self-attention (SA) mechanism for multi-station passenger flow prediction. A dynamic graph convolutional network (DGCN) is applied for the spatial feature extraction, and gated recurrent unit (GRU) is combined to learn the temporal features. SA is applied to further assign the weights for the extracted spatio-temporal features. The Experiment has been conducted on the passenger flow in the Xiamen bus rapid transit (BRT). The results demonstrate that the proposed DSTNet with SA (SA-DSTNet) outperforms the baselines in the multi-station passenger flow prediction task.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exemplary Sequence Cardinality: An Effective Application for Word Spotting

Exemplary Sequence Cardinality: An Effective Application for...

引用

International Conference on Document Analysis and recognition

作者： Tanmoy Mondal Nicolas Ragot Jean-Yves Ramel Umapada Pal Université Fran?ois Rabelais Tours Laboratory of Computer Science (LI) Tours France. Indian Statistical Institute Computer Vision and Pattern Recognition Unit Kolkata India.

ISBN: (纸本)9781479918065

In this paper, a new sequence matching algorithm called as Exemplary Sequence Cardinality (ESC) is proposed. ESC combines several abilities of other sequence matching algorithms e.g. DTW, SSDTW, CDP, FSM, MVM, OSB~1. Depending on the application domain, ESC can be tuned to behave such as these different sequence matching algorithms. Its generality and robustness comes from its ability to find subsequences (as in CDP and SSDTW), to skip outliers inside the target sequences (as in MVM and FSM) and also in the query sequence (as in OSB) and it has the ability to have many to one and one to many correspondences (as in DTW) between the elements of the query and the target sequences. It's special characteristic of skipping noisy elements from query sequence along with other afore mentioned properties gives it an edge over FSM. In case of word spotting application, the outliers skipping capability of ESC makes it less sensible to local variations in the spelling of words, and also to noise present in the query and/or in the target word images. Due to it's capability of sub-sequence matching, the ESC algorithm has the ability to retrieve a query inside a line or piece of line. Finally, its multiple matching facilities (many to one and one to many matching) is proven to be well advantageous in case of different length of target and query sequences due to the variability in scale, font, type/size factors. By experimenting on printed historical document images, we have demonstrated the interest of proposed ESC algorithm in specific cases when incorrect word segmentation and word level local variations occur regularly.

关键词： Word spotting Elastic sequence matching Minimal variance matching (MVM) Optimal sequence bijection (OSB) Dynamic time warping (DTW) Continuous dynamic programming (CDP) Flexible sequence matching (FSM)

来源：评论

学校读者我要写书评

暂无评论

EDEN: Deep Feature Distribution Pooling for Saimaa Ringed Seals pattern Matching 2nd

EDEN: Deep Feature Distribution Pooling for Saimaa Ringed Se...

引用

2nd International Conference on Cyber-Physical Systems and Control, CPS and C 2021

作者： Chelak, Ilia Nepovinnykh, Ekaterina Eerola, Tuomas Kälviäinen, Heikki Belykh, Igor Peter the Great St. Petersburg Polytechnic University Politechnicheskaya St. 29 St. Petersburg195251 Russia Computer Vision and Pattern Recognition Laboratory Department of Computational Engineering School of Engineering Science Lappeenranta-Lahti University of Technology LUT P.O. Box 20 Lappeenranta53850 Finland

ISBN: (纸本)9783031208744

In this paper, pelage pattern matching is considered to solve the individual re-identification of the Saimaa ringed seals. Animal reidentification, together with the access to a large amount of image material through camera traps and crowd-sourcing, provides novel possibilities for animal monitoring and conservation. Image retrieval techniques, such as global pooling, can be used to solve the individual re-identification. However, current global pooling methods incorporate only value distribution of features, losing spatial information. To overcome the problem, we propose a novel pooling approach that allows aggregating the local pattern features to get a fixed size embedding vector that incorporates global features by taking into account their spatial distribution. This is obtained by eigen decomposition of covariances computed for probability mass functions representing feature maps. Embedding vectors can then be used to find the best match in the database of known individuals allowing animal re-identification. The results show that the proposed pooling technique outperforms the existing methods on the challenging Saimaa ringed seal image data. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Animal biometrics Global pooling pattern matching Saimaa ringed seals

来源：评论

学校读者我要写书评

暂无评论

Region-based Image Annotation using Asymmetrical Support Vector Machine-based Multiple-Instance Learning

Region-based Image Annotation using Asymmetrical Support Vec...

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Changbo Yang Ming Dong Jing Hua Machine Vision and Pattern Recognition Laboratory Department of Computer Science Wayne State University Detroit MI USA Department of Computer Science Wayne State University Detroit MI USA

In region-based image annotation, keywords are usually associated with images instead of individual regions in the training data set. This poses a major challenge for any learning strategy. In this paper, we formulate image annotation as a supervised learning problem under Multiple-Instance Learning (MIL) framework. We present a novel Asymmetrical Support Vector Machine-based MIL algorithm (ASVM-MIL), which extends the conventional Support Vector Machine (SVM) to the MIL setting by introducing asymmetrical loss functions for false positives and false negatives. The proposed ASVM-MIL algorithm is evaluated on both image annotation data sets and the benchmark MUSK data sets.

关键词： Machine learning Support vector machines Image retrieval pattern recognition computer science Training data Supervised learning computer vision Feature extraction Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models

Generate Like Experts: Multi-Stage Font Generation by Incorp...

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Bin Fu Fanghua Yu Anran Liu Zixuan Wang Jie Wen Junjun He Yu Qiao ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences The University of Hong Kong Harbin Institute of Technology Shenzhen Shanghai Artificial Intelligence Laboratory

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Few-shot font generation (FFG) produces stylized font images with a limited number of reference samples, which can significantly reduce labor costs in manual font designs. Most existing FFG methods follow the style-content dis-entanglement paradigm and employ the Generative Adver-sarial Network (GAN) to generate target fonts by combining the decoupled content and style representations. The complicated structure and detailed style are simultaneously generated in those methods, which may be the sub-optimal solutions for FFG task. Inspired by most manual font design processes of expert designers, in this paper, we model font generation as a multi-stage generative process. Specifically, as the injected noise and the data distribution in diffusion models can be well-separated into different sub-spaces, we are able to incorporate the font transfer process into these models. Based on this observation, we generalize diffusion methods to modelfont generative process by separating the reverse diffusion process into three stages with different functions: The structure construction stage first generates the structure information for the target character based on the source image, and the font transfer stage subsequently transforms the source font to the target font. Finally, the font refinement stage enhances the appearances and local details of the target font images. Based on the above multi-stage generative process, we construct our font generation framework. named MSD-Font, with a dual-network approach to generate font images. The superior performance demonstrates the effectiveness of our model. The code is available at: https://***/fubinfbIMSD-Font.

关键词： Costs Noise Diffusion processes Transforms Manuals Diffusion models Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Introduction

SpringerBriefs in Applied Sciences and Technology

引用

SpringerBriefs in Applied Sciences and Technology 2018年第9789811065286期 1-12页

作者： Gurumoorthy, Sasikumar Muppalaneni, Naresh Babu Gao, Xiao-Zhi Department of Computer Science and Systems Engineering Sree Vidyanikethan Engineering College Tirupati India Machine Vision and Pattern Recognition Laboratory Lappeenranta University of Technology Lappeenranta Finland

The EEG is a measure of voltage as a function of time. The voltage of the EEG regulates its amplitude (measured from peak to peak). EEG amplitudes in the cortex range start from 500 to 1500 μV, but the amplitude...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Activating More Pixels in Image Super-Resolution Transformer

Activating More Pixels in Image Super-Resolution Transformer

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Xiangyu Chen Xintao Wang Jiantao Zhou Yu Qiao Chao Dong State Key Laboratory of Internet of Things for Smart City University of Macau Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shanghai Artificial Intelligence Laboratory ARC Lab Tencent PCG

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better reconstruction, we propose a novel Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of being able to utilize global statistics and strong local fitting capability. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to exploit the potential of the model for further improvement. Extensive experiments show the effectiveness of the proposed modules, and we further scale up the model to demonstrate that the performance of this task can be greatly improved. Our overall method significantly outperforms the state-of-the-art methods by more than 1dB.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multiple Classifier Systems 1

引用

丛书名： Lecture Notes in computer Science

1000年

作者： Nikunj C. Oza Robi Polikar Josef Kittler Fabio Roli

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：